ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents

Computer Science > Artificial Intelligence [Submitted on 25 Mar 2026] ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents Bingqing Wei, Zhongyu Xia, Dingai Liu, Xiaoyu Zhou, Zhiwei Lin, Yongtao Wang Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a fundamental gap between the static training data of VLMs and the physical interaction for embodied tasks. VLMs can learn rich semantic knowledge from static data but lack the ability to interact with the world. To address this issue, we introduce ELITE, an embodied agent framework with {E}xperiential {L}earning and {I}ntent-aware {T}ransfer that enables agents to continuously learn from their own environment interaction experiences, and transfer acquired knowledge to procedurally similar tasks. ELITE operates through two synergistic mechanisms, \textit{i.e.,} self-reflective knowledge construction and intent-aware retrieval. Specifically, self-reflective knowledge construction extracts reusable strategies from execution trajectories and maintains an evolving strategy pool through structured refinement operations. Then, intent-aware retrieval identifies relevant strategies from the pool and applies them to current tasks. Experiments on the EB-ALFRED and EB-Habitat benchmarks show that ELITE achieves 9\% and 5\% performance improvement over base VLMs in the online setting without any supervision. In the supervised setting, ELITE generalizes effectively to unseen task categories, achieving better performance compared to state-of-the-art training-based methods. These results demonstrate the effectiveness of ELITE for bridging the gap between semantic understanding and reliable action execution. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.24018 [cs.AI]   (or arXiv:2603.24018v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.24018 Focus to learn more Submission history From: Bingqing Wei [view email] [v1] Wed, 25 Mar 2026 07:25:51 UTC (721 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)